CVE-2026-126396
Awaiting Analysis Awaiting Analysis - Queue

vLLM Video Processor Resource Exhaustion via Unvalidated min_pixels

Publication date: 2026-11-13

Last updated on: 2026-11-13

Assigner: VulnCheck

Description
vLLM from 0.24.0 before 0.31.0 contains a resource exhaustion vulnerability in the MiniMax M3 VL video processor, which accepts request-level min_pixels without range or min_pixels <= max_pixels validation. Its video-wide pixel budget is enforced only when max_long_side_pixel is set, and that value defaults to None. API clients can supply a large min_pixels via mm_processor_kwargs to enlarge every decoded frame, causing excessive CPU and host-memory consumption that may disrupt workers or the service.

CVSS Scores

EPSS Scores

Probability:
Percentile:

Meta Information

Published
2026-11-13
Last Modified
2026-11-13
Generated
2026-11-13
AI Q&A
2026-11-13
EPSS Evaluated
N/A
NVD
CVE-2026-126396
EUVD
EUVD-2026-125169

Affected Vendors & Products

Showing 1 associated CPE
Vendor Product Version / Range
vllm_project vllm From 0.24.0 (inc) to 0.31.0 (exc)

Helpful Resources

Exploitability

CWE
CWE Icon
KEV
KEV Icon
CWE ID Description
CWE-770 The product allocates a reusable resource or group of resources on behalf of an actor without imposing any intended restrictions on the size or number of resources that can be allocated.

Attack-Flow Graph

AI Quick Actions

Instant insights powered by AI
Executive Summary

This vulnerability is a resource exhaustion issue in vLLM versions 0.24.0 to 0.30.9. It involves the MiniMax M3 video processor accepting a large min_pixels value in the mm_processor_kwargs parameter without validation. This causes video frames to be enlarged beyond safe limits, leading to excessive CPU and memory usage that can disrupt workers or the service.

Detection Guidance

To detect this vulnerability, monitor for unusually high CPU or memory usage during video processing tasks in vLLM versions 0.24.0 to 0.30.9. Check API logs for requests containing large min_pixels values in mm_processor_kwargs. Use system monitoring tools like top, htop, or ps to observe resource consumption spikes during video decoding operations.

Impact Analysis

The vulnerability can cause service disruption by consuming excessive CPU and host memory. This may lead to allocation failures or temporary downtime for the vLLM service or workers. It does not directly compromise data confidentiality or integrity.

Mitigation Strategies

Immediately upgrade vLLM to version 0.31.0 or later to apply the patch that blocks untrusted mm_processor_kwargs by default. If upgrading is not possible, restrict API access to trusted clients only and implement input validation to reject requests with excessively large min_pixels values. Monitor system resources closely for signs of resource exhaustion.

Chat Assistant

Ask questions about this CVE
Hi! I’m here to help you understand CVE-2026-126396. Ask me anything about the vulnerability, its impact, or mitigation strategies.
0/70

EPSS Chart

Security Radar

News mentioning this vulnerability
Loading related security news...